ScanNet200 3D Semantic Label Benchmark
The 3D semantic labeling task involves predicting a semantic labeling of a 3D scan mesh.
Evaluation and metricsOur evaluation ranks all methods according to the PASCAL VOC intersection-over-union metric (IoU). IoU = TP/(TP+FP+FN), where TP, FP, and FN are the numbers of true positive, false positive, and false negative pixels, respectively. Predicted labels are evaluated per-vertex over the respective 3D scan mesh; for 3D approaches that operate on other representations like grids or points, the predicted labels should be mapped onto the mesh vertices (e.g., one such example for grid to mesh vertices is provided in the evaluation helpers).
This table lists the benchmark results for the ScanNet200 3D semantic label scenario.
Method | Info | avg iou | head iou | common iou | tail iou | wall | chair | floor | table | door | couch | cabinet | shelf | desk | office chair | bed | pillow | sink | picture | window | toilet | bookshelf | monitor | curtain | book | armchair | coffee table | box | refrigerator | lamp | kitchen cabinet | towel | clothes | tv | nightstand | counter | dresser | stool | cushion | plant | ceiling | bathtub | end table | dining table | keyboard | bag | backpack | toilet paper | printer | tv stand | whiteboard | blanket | shower curtain | trash can | closet | stairs | microwave | stove | shoe | computer tower | bottle | bin | ottoman | bench | board | washing machine | mirror | copier | basket | sofa chair | file cabinet | fan | laptop | shower | paper | person | paper towel dispenser | oven | blinds | rack | plate | blackboard | piano | suitcase | rail | radiator | recycling bin | container | wardrobe | soap dispenser | telephone | bucket | clock | stand | light | laundry basket | pipe | clothes dryer | guitar | toilet paper holder | seat | speaker | column | bicycle | ladder | bathroom stall | shower wall | cup | jacket | storage bin | coffee maker | dishwasher | paper towel roll | machine | mat | windowsill | bar | toaster | bulletin board | ironing board | fireplace | soap dish | kitchen counter | doorframe | toilet paper dispenser | mini fridge | fire extinguisher | ball | hat | shower curtain rod | water cooler | paper cutter | tray | shower door | pillar | ledge | toaster oven | mouse | toilet seat cover dispenser | furniture | cart | storage container | scale | tissue box | light switch | crate | power outlet | decoration | sign | projector | closet door | vacuum cleaner | candle | plunger | stuffed animal | headphones | dish rack | broom | guitar case | range hood | dustpan | hair dryer | water bottle | handicap bar | purse | vent | shower floor | water pitcher | mailbox | bowl | paper bag | alarm clock | music stand | projector screen | divider | laundry detergent | bathroom counter | object | bathroom vanity | closet wall | laundry hamper | bathroom stall door | ceiling light | trash bin | dumbbell | stair rail | tube | bathroom cabinet | cd case | closet rod | coffee kettle | structure | shower head | keyboard piano | case of water bottles | coat rack | storage organizer | folded chair | fire alarm | power strip | calendar | poster | potted plant | luggage | mattress |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
ALS-MinkowskiNet | 0.414 1 | 0.610 1 | 0.322 2 | 0.271 1 | 0.852 1 | 0.710 1 | 0.973 1 | 0.572 2 | 0.719 2 | 0.795 1 | 0.477 4 | 0.506 1 | 0.601 1 | 0.000 10 | 0.804 4 | 0.646 2 | 0.804 1 | 0.344 2 | 0.777 1 | 0.984 1 | 0.671 1 | 0.879 2 | 0.936 1 | 0.342 3 | 0.632 5 | 0.449 2 | 0.817 3 | 0.475 6 | 0.723 1 | 0.798 1 | 0.376 7 | 0.832 1 | 0.693 1 | 0.031 8 | 0.564 1 | 0.510 10 | 0.000 1 | 0.893 1 | 0.905 1 | 0.672 13 | 0.314 1 | 0.000 7 | 0.718 1 | 0.153 1 | 0.542 1 | 0.397 2 | 0.726 2 | 0.752 7 | 0.252 6 | 0.226 1 | 0.916 1 | 0.800 1 | 0.047 12 | 0.807 2 | 0.769 1 | 0.709 2 | 0.630 2 | 0.769 1 | 0.217 8 | 0.000 3 | 0.285 1 | 0.598 3 | 0.846 8 | 0.535 1 | 0.956 2 | 0.000 3 | 0.137 8 | 0.784 1 | 0.464 5 | 0.463 10 | 0.230 8 | 0.000 1 | 0.598 2 | 0.662 6 | 0.000 4 | 0.087 2 | 0.000 1 | 0.135 1 | 0.900 1 | 0.780 10 | 0.703 1 | 0.741 1 | 0.571 2 | 0.149 9 | 0.697 3 | 0.646 1 | 0.000 3 | 0.076 1 | 0.000 1 | 0.025 7 | 0.000 3 | 0.106 4 | 0.981 1 | 0.000 1 | 0.043 5 | 0.113 3 | 0.888 1 | 0.248 12 | 0.404 3 | 0.252 4 | 0.314 1 | 0.220 5 | 0.245 1 | 0.466 6 | 0.366 1 | 0.159 2 | 0.000 3 | 0.149 5 | 0.690 2 | 0.000 1 | 0.531 2 | 0.253 1 | 0.285 4 | 0.460 1 | 0.440 4 | 0.813 1 | 0.230 1 | 0.283 4 | 0.159 9 | 0.000 1 | 0.728 1 | 0.666 4 | 0.958 1 | 0.000 1 | 0.021 4 | 0.252 4 | 0.118 3 | 0.000 5 | 0.445 3 | 0.223 9 | 0.285 1 | 0.194 3 | 0.390 2 | 0.000 1 | 0.475 1 | 0.842 7 | 0.000 1 | 0.455 3 | 0.000 1 | 0.250 4 | 0.458 7 | 0.000 1 | 0.865 1 | 0.000 1 | 0.000 1 | 0.635 1 | 0.359 2 | 0.972 1 | 0.087 2 | 0.447 1 | 0.000 1 | 0.000 5 | 0.000 1 | 0.129 2 | 0.532 5 | 0.446 6 | 0.503 3 | 0.071 11 | 0.135 11 | 0.699 3 | 0.717 1 | 0.097 1 | 0.000 1 | 0.665 1 | 0.000 2 | 0.000 2 | 1.000 1 | 0.752 4 | 0.000 2 | 0.000 1 | 0.000 1 | 0.142 8 | 0.200 1 | 0.259 1 | 1.000 1 | 0.000 1 | |||||||||||||||||||||||||||||
OA-CNN-L_ScanNet200 | 0.333 7 | 0.558 3 | 0.269 7 | 0.124 9 | 0.821 4 | 0.703 2 | 0.946 5 | 0.569 3 | 0.662 3 | 0.748 7 | 0.487 2 | 0.455 2 | 0.572 5 | 0.000 10 | 0.789 6 | 0.534 7 | 0.736 7 | 0.271 4 | 0.713 3 | 0.949 5 | 0.498 12 | 0.877 3 | 0.860 7 | 0.332 5 | 0.706 1 | 0.474 1 | 0.788 6 | 0.406 9 | 0.637 4 | 0.495 7 | 0.355 8 | 0.805 4 | 0.592 10 | 0.015 12 | 0.396 4 | 0.602 5 | 0.000 1 | 0.799 7 | 0.876 6 | 0.713 12 | 0.276 2 | 0.000 7 | 0.493 9 | 0.080 7 | 0.448 11 | 0.363 3 | 0.661 3 | 0.833 5 | 0.262 4 | 0.125 5 | 0.823 8 | 0.665 7 | 0.076 7 | 0.720 5 | 0.557 7 | 0.637 7 | 0.517 7 | 0.672 9 | 0.227 6 | 0.000 3 | 0.158 9 | 0.496 5 | 0.843 9 | 0.352 8 | 0.835 9 | 0.000 3 | 0.103 11 | 0.711 4 | 0.527 2 | 0.526 5 | 0.320 5 | 0.000 1 | 0.568 5 | 0.625 8 | 0.067 1 | 0.000 7 | 0.000 1 | 0.001 3 | 0.806 4 | 0.836 6 | 0.621 8 | 0.591 6 | 0.373 7 | 0.314 5 | 0.668 6 | 0.398 7 | 0.003 2 | 0.000 6 | 0.000 1 | 0.016 12 | 0.024 2 | 0.043 11 | 0.906 5 | 0.000 1 | 0.052 4 | 0.000 9 | 0.384 8 | 0.330 9 | 0.342 6 | 0.100 8 | 0.223 5 | 0.183 9 | 0.112 5 | 0.476 5 | 0.313 6 | 0.130 8 | 0.196 2 | 0.112 8 | 0.370 10 | 0.000 1 | 0.234 8 | 0.071 7 | 0.160 5 | 0.403 4 | 0.398 10 | 0.492 11 | 0.197 3 | 0.076 9 | 0.272 3 | 0.000 1 | 0.200 13 | 0.560 7 | 0.735 4 | 0.000 1 | 0.000 8 | 0.000 8 | 0.110 6 | 0.002 4 | 0.021 7 | 0.412 5 | 0.000 8 | 0.000 5 | 0.000 9 | 0.000 1 | 0.000 2 | 0.794 8 | 0.000 1 | 0.445 4 | 0.000 1 | 0.022 7 | 0.509 6 | 0.000 1 | 0.517 11 | 0.000 1 | 0.000 1 | 0.001 13 | 0.245 3 | 0.915 5 | 0.024 3 | 0.089 4 | 0.000 1 | 0.262 2 | 0.000 1 | 0.103 9 | 0.524 6 | 0.392 9 | 0.515 2 | 0.013 13 | 0.251 4 | 0.411 11 | 0.662 2 | 0.001 8 | 0.000 1 | 0.473 9 | 0.000 2 | 0.000 2 | 0.150 5 | 0.699 7 | 0.000 2 | 0.000 1 | 0.000 1 | 0.166 5 | 0.000 5 | 0.024 2 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
CeCo | 0.340 5 | 0.551 7 | 0.247 9 | 0.181 4 | 0.784 9 | 0.661 10 | 0.939 9 | 0.564 4 | 0.624 9 | 0.721 8 | 0.484 3 | 0.429 3 | 0.575 3 | 0.027 6 | 0.774 8 | 0.503 10 | 0.753 4 | 0.242 9 | 0.656 9 | 0.945 6 | 0.534 6 | 0.865 6 | 0.860 7 | 0.177 13 | 0.616 6 | 0.400 3 | 0.818 2 | 0.579 1 | 0.615 7 | 0.367 10 | 0.408 5 | 0.726 11 | 0.633 3 | 0.162 1 | 0.360 5 | 0.619 2 | 0.000 1 | 0.828 5 | 0.873 8 | 0.924 2 | 0.109 9 | 0.083 3 | 0.564 4 | 0.057 13 | 0.475 9 | 0.266 7 | 0.781 1 | 0.767 6 | 0.257 5 | 0.100 9 | 0.825 7 | 0.663 8 | 0.048 11 | 0.620 10 | 0.551 8 | 0.595 11 | 0.532 6 | 0.692 7 | 0.246 4 | 0.000 3 | 0.213 5 | 0.615 1 | 0.861 5 | 0.376 6 | 0.900 4 | 0.000 3 | 0.102 12 | 0.660 6 | 0.321 11 | 0.547 4 | 0.226 9 | 0.000 1 | 0.311 9 | 0.742 2 | 0.011 3 | 0.006 6 | 0.000 1 | 0.000 4 | 0.546 11 | 0.824 7 | 0.345 10 | 0.665 2 | 0.450 5 | 0.435 1 | 0.683 4 | 0.411 6 | 0.338 1 | 0.000 6 | 0.000 1 | 0.030 6 | 0.000 3 | 0.068 7 | 0.892 6 | 0.000 1 | 0.063 3 | 0.000 9 | 0.257 9 | 0.304 10 | 0.387 4 | 0.079 10 | 0.228 4 | 0.190 8 | 0.000 12 | 0.586 1 | 0.347 3 | 0.133 6 | 0.000 3 | 0.037 9 | 0.377 9 | 0.000 1 | 0.384 5 | 0.006 12 | 0.003 9 | 0.421 3 | 0.410 9 | 0.643 5 | 0.171 5 | 0.121 5 | 0.142 10 | 0.000 1 | 0.510 9 | 0.447 8 | 0.474 10 | 0.000 1 | 0.000 8 | 0.286 3 | 0.083 9 | 0.000 5 | 0.000 8 | 0.603 1 | 0.096 5 | 0.063 4 | 0.000 9 | 0.000 1 | 0.000 2 | 0.898 3 | 0.000 1 | 0.429 5 | 0.000 1 | 0.400 1 | 0.550 3 | 0.000 1 | 0.633 5 | 0.000 1 | 0.000 1 | 0.377 4 | 0.000 11 | 0.916 4 | 0.000 6 | 0.000 7 | 0.000 1 | 0.000 5 | 0.000 1 | 0.102 10 | 0.499 8 | 0.296 10 | 0.463 4 | 0.089 5 | 0.304 1 | 0.740 2 | 0.401 12 | 0.010 4 | 0.000 1 | 0.560 3 | 0.000 2 | 0.000 2 | 0.709 2 | 0.652 8 | 0.000 2 | 0.000 1 | 0.000 1 | 0.143 7 | 0.000 5 | 0.000 3 | 0.609 3 | 0.000 1 | |||||||||||||||||||||||||||||
Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia: Understanding Imbalanced Semantic Segmentation Through Neural Collapse. CVPR 2023 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
OctFormer ScanNet200 | 0.326 9 | 0.539 8 | 0.265 8 | 0.131 8 | 0.806 7 | 0.670 9 | 0.943 8 | 0.535 8 | 0.662 3 | 0.705 12 | 0.423 7 | 0.407 4 | 0.505 9 | 0.003 8 | 0.765 9 | 0.582 6 | 0.686 11 | 0.227 12 | 0.680 6 | 0.943 7 | 0.601 2 | 0.854 9 | 0.892 4 | 0.335 4 | 0.417 13 | 0.357 8 | 0.724 8 | 0.453 7 | 0.632 5 | 0.596 3 | 0.432 3 | 0.783 7 | 0.512 12 | 0.021 11 | 0.244 11 | 0.637 1 | 0.000 1 | 0.787 8 | 0.873 8 | 0.743 10 | 0.000 13 | 0.000 7 | 0.534 7 | 0.110 2 | 0.499 5 | 0.289 6 | 0.626 5 | 0.620 10 | 0.168 13 | 0.204 2 | 0.849 6 | 0.679 6 | 0.117 3 | 0.633 8 | 0.684 3 | 0.650 6 | 0.552 4 | 0.684 8 | 0.312 2 | 0.000 3 | 0.175 8 | 0.429 8 | 0.865 3 | 0.413 3 | 0.837 8 | 0.000 3 | 0.145 6 | 0.626 7 | 0.451 6 | 0.487 8 | 0.513 1 | 0.000 1 | 0.529 6 | 0.613 9 | 0.000 4 | 0.033 4 | 0.000 1 | 0.000 4 | 0.828 3 | 0.871 2 | 0.622 7 | 0.587 7 | 0.411 6 | 0.137 10 | 0.645 10 | 0.343 8 | 0.000 3 | 0.000 6 | 0.000 1 | 0.022 9 | 0.000 3 | 0.026 13 | 0.829 9 | 0.000 1 | 0.022 6 | 0.089 5 | 0.842 2 | 0.253 11 | 0.318 9 | 0.296 2 | 0.178 7 | 0.291 3 | 0.224 2 | 0.584 2 | 0.200 10 | 0.132 7 | 0.000 3 | 0.128 7 | 0.227 12 | 0.000 1 | 0.230 9 | 0.047 9 | 0.149 6 | 0.331 8 | 0.412 8 | 0.618 6 | 0.164 6 | 0.102 7 | 0.522 1 | 0.000 1 | 0.655 4 | 0.378 9 | 0.469 11 | 0.000 1 | 0.000 8 | 0.000 8 | 0.105 7 | 0.000 5 | 0.000 8 | 0.483 3 | 0.000 8 | 0.000 5 | 0.028 6 | 0.000 1 | 0.000 2 | 0.906 1 | 0.000 1 | 0.339 11 | 0.000 1 | 0.000 9 | 0.457 8 | 0.000 1 | 0.612 6 | 0.000 1 | 0.000 1 | 0.408 3 | 0.000 11 | 0.900 7 | 0.000 6 | 0.000 7 | 0.000 1 | 0.029 4 | 0.000 1 | 0.074 13 | 0.455 11 | 0.479 4 | 0.427 5 | 0.079 8 | 0.140 8 | 0.496 7 | 0.414 10 | 0.022 3 | 0.000 1 | 0.471 10 | 0.000 2 | 0.000 2 | 0.000 8 | 0.722 5 | 0.000 2 | 0.000 1 | 0.000 1 | 0.138 10 | 0.000 5 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
Peng-Shuai Wang: OctFormer: Octree-based Transformers for 3D Point Clouds. SIGGRAPH 2023 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
PTv3 ScanNet200 | 0.393 2 | 0.592 2 | 0.330 1 | 0.216 2 | 0.851 2 | 0.687 5 | 0.971 2 | 0.586 1 | 0.755 1 | 0.752 6 | 0.505 1 | 0.404 5 | 0.575 3 | 0.000 10 | 0.848 1 | 0.616 3 | 0.761 2 | 0.349 1 | 0.738 2 | 0.978 2 | 0.546 5 | 0.860 7 | 0.926 2 | 0.346 2 | 0.654 3 | 0.384 5 | 0.828 1 | 0.523 3 | 0.699 2 | 0.583 4 | 0.387 6 | 0.822 2 | 0.688 2 | 0.118 4 | 0.474 2 | 0.603 4 | 0.000 1 | 0.832 4 | 0.903 2 | 0.753 8 | 0.140 7 | 0.000 7 | 0.650 3 | 0.109 3 | 0.520 2 | 0.457 1 | 0.497 8 | 0.871 3 | 0.281 2 | 0.192 3 | 0.887 3 | 0.748 2 | 0.168 1 | 0.727 4 | 0.733 2 | 0.740 1 | 0.644 1 | 0.714 4 | 0.190 9 | 0.000 3 | 0.256 3 | 0.449 7 | 0.914 1 | 0.514 2 | 0.759 11 | 0.337 1 | 0.172 4 | 0.692 5 | 0.617 1 | 0.636 1 | 0.325 4 | 0.000 1 | 0.641 1 | 0.782 1 | 0.000 4 | 0.065 3 | 0.000 1 | 0.000 4 | 0.842 2 | 0.903 1 | 0.661 3 | 0.662 3 | 0.612 1 | 0.405 2 | 0.731 1 | 0.566 2 | 0.000 3 | 0.000 6 | 0.000 1 | 0.017 11 | 0.301 1 | 0.088 5 | 0.941 2 | 0.000 1 | 0.077 2 | 0.000 9 | 0.717 4 | 0.790 1 | 0.310 10 | 0.026 13 | 0.264 3 | 0.349 1 | 0.220 3 | 0.397 9 | 0.366 1 | 0.115 9 | 0.000 3 | 0.337 1 | 0.463 6 | 0.000 1 | 0.531 2 | 0.218 2 | 0.593 1 | 0.455 2 | 0.469 1 | 0.708 3 | 0.210 2 | 0.592 2 | 0.108 12 | 0.000 1 | 0.728 1 | 0.682 2 | 0.671 5 | 0.000 1 | 0.000 8 | 0.407 1 | 0.136 2 | 0.022 2 | 0.575 1 | 0.436 4 | 0.259 3 | 0.428 1 | 0.048 4 | 0.000 1 | 0.000 2 | 0.879 5 | 0.000 1 | 0.480 2 | 0.000 1 | 0.133 6 | 0.597 1 | 0.000 1 | 0.690 2 | 0.000 1 | 0.000 1 | 0.009 12 | 0.000 11 | 0.921 3 | 0.000 6 | 0.151 3 | 0.000 1 | 0.000 5 | 0.000 1 | 0.109 7 | 0.494 10 | 0.622 2 | 0.394 7 | 0.073 10 | 0.141 7 | 0.798 1 | 0.528 4 | 0.026 2 | 0.000 1 | 0.551 4 | 0.000 2 | 0.000 2 | 0.134 6 | 0.717 6 | 0.000 2 | 0.000 1 | 0.000 1 | 0.188 3 | 0.000 5 | 0.000 3 | 0.791 2 | 0.000 1 | |||||||||||||||||||||||||||||
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang, Zhijian Liu, Xihui Liu, Yu Qiao, Wanli Ouyang, Tong He, Hengshuang Zhao: Point Transformer V3: Simpler, Faster, Stronger. CVPR 2024 (Oral) | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
BFANet ScanNet200 | 0.360 3 | 0.553 5 | 0.293 3 | 0.193 3 | 0.827 3 | 0.689 3 | 0.970 3 | 0.528 9 | 0.661 5 | 0.753 5 | 0.436 6 | 0.378 6 | 0.469 11 | 0.042 5 | 0.810 2 | 0.654 1 | 0.760 3 | 0.266 6 | 0.659 8 | 0.973 3 | 0.574 3 | 0.849 10 | 0.897 3 | 0.382 1 | 0.546 9 | 0.372 7 | 0.698 10 | 0.491 5 | 0.617 6 | 0.526 6 | 0.436 1 | 0.764 10 | 0.476 13 | 0.101 5 | 0.409 3 | 0.585 7 | 0.000 1 | 0.835 2 | 0.901 3 | 0.810 5 | 0.102 10 | 0.000 7 | 0.688 2 | 0.096 4 | 0.483 7 | 0.264 8 | 0.612 7 | 0.591 12 | 0.358 1 | 0.161 4 | 0.863 4 | 0.707 3 | 0.128 2 | 0.814 1 | 0.669 4 | 0.629 8 | 0.563 3 | 0.651 11 | 0.258 3 | 0.000 3 | 0.194 7 | 0.494 6 | 0.806 10 | 0.394 5 | 0.953 3 | 0.000 3 | 0.233 1 | 0.757 3 | 0.508 4 | 0.556 3 | 0.476 2 | 0.000 1 | 0.573 4 | 0.741 3 | 0.000 4 | 0.000 7 | 0.000 1 | 0.000 4 | 0.000 13 | 0.852 4 | 0.678 2 | 0.616 4 | 0.460 4 | 0.338 3 | 0.710 2 | 0.534 3 | 0.000 3 | 0.025 3 | 0.000 1 | 0.043 2 | 0.000 3 | 0.056 10 | 0.493 13 | 0.000 1 | 0.000 8 | 0.109 4 | 0.785 3 | 0.590 3 | 0.298 11 | 0.282 3 | 0.143 9 | 0.262 4 | 0.053 9 | 0.526 4 | 0.337 4 | 0.215 1 | 0.000 3 | 0.135 6 | 0.510 4 | 0.000 1 | 0.596 1 | 0.043 10 | 0.511 2 | 0.321 10 | 0.459 2 | 0.772 2 | 0.124 9 | 0.060 10 | 0.266 4 | 0.000 1 | 0.574 7 | 0.568 6 | 0.653 7 | 0.000 1 | 0.093 1 | 0.298 2 | 0.239 1 | 0.000 5 | 0.516 2 | 0.129 10 | 0.284 2 | 0.000 5 | 0.431 1 | 0.000 1 | 0.000 2 | 0.848 6 | 0.000 1 | 0.492 1 | 0.000 1 | 0.376 2 | 0.522 5 | 0.000 1 | 0.469 13 | 0.000 1 | 0.000 1 | 0.330 5 | 0.151 6 | 0.875 11 | 0.000 6 | 0.254 2 | 0.000 1 | 0.000 5 | 0.000 1 | 0.088 11 | 0.661 1 | 0.481 3 | 0.255 10 | 0.105 1 | 0.139 9 | 0.666 4 | 0.641 3 | 0.000 9 | 0.000 1 | 0.614 2 | 0.000 2 | 0.000 2 | 0.000 8 | 0.921 1 | 0.000 2 | 0.000 1 | 0.000 1 | 0.497 1 | 0.000 5 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
PPT-SpUNet-F.T. | 0.332 8 | 0.556 4 | 0.270 5 | 0.123 10 | 0.816 5 | 0.682 6 | 0.946 5 | 0.549 6 | 0.657 7 | 0.756 4 | 0.459 5 | 0.376 7 | 0.550 7 | 0.001 9 | 0.807 3 | 0.616 3 | 0.727 8 | 0.267 5 | 0.691 4 | 0.942 8 | 0.530 8 | 0.872 5 | 0.874 6 | 0.330 6 | 0.542 10 | 0.374 6 | 0.792 4 | 0.400 10 | 0.673 3 | 0.572 5 | 0.433 2 | 0.793 5 | 0.623 5 | 0.008 13 | 0.351 6 | 0.594 6 | 0.000 1 | 0.783 9 | 0.876 6 | 0.833 4 | 0.213 4 | 0.000 7 | 0.537 6 | 0.091 5 | 0.519 3 | 0.304 5 | 0.620 6 | 0.942 1 | 0.264 3 | 0.124 6 | 0.855 5 | 0.695 4 | 0.086 6 | 0.646 7 | 0.506 12 | 0.658 5 | 0.535 5 | 0.715 3 | 0.314 1 | 0.000 3 | 0.241 4 | 0.608 2 | 0.897 2 | 0.359 7 | 0.858 7 | 0.000 3 | 0.076 13 | 0.611 9 | 0.392 8 | 0.509 6 | 0.378 3 | 0.000 1 | 0.579 3 | 0.565 12 | 0.000 4 | 0.000 7 | 0.000 1 | 0.000 4 | 0.755 5 | 0.806 8 | 0.661 3 | 0.572 11 | 0.350 8 | 0.181 7 | 0.660 8 | 0.300 10 | 0.000 3 | 0.000 6 | 0.000 1 | 0.023 8 | 0.000 3 | 0.042 12 | 0.930 3 | 0.000 1 | 0.000 8 | 0.077 6 | 0.584 5 | 0.392 7 | 0.339 7 | 0.185 6 | 0.171 8 | 0.308 2 | 0.006 11 | 0.563 3 | 0.256 7 | 0.150 3 | 0.000 3 | 0.002 12 | 0.345 11 | 0.000 1 | 0.045 10 | 0.197 3 | 0.063 7 | 0.323 9 | 0.453 3 | 0.600 7 | 0.163 7 | 0.037 11 | 0.349 2 | 0.000 1 | 0.672 3 | 0.679 3 | 0.753 2 | 0.000 1 | 0.000 8 | 0.000 8 | 0.117 4 | 0.000 5 | 0.000 8 | 0.291 8 | 0.000 8 | 0.000 5 | 0.039 5 | 0.000 1 | 0.000 2 | 0.899 2 | 0.000 1 | 0.374 9 | 0.000 1 | 0.000 9 | 0.545 4 | 0.000 1 | 0.634 4 | 0.000 1 | 0.000 1 | 0.074 9 | 0.223 4 | 0.914 6 | 0.000 6 | 0.021 5 | 0.000 1 | 0.000 5 | 0.000 1 | 0.112 5 | 0.498 9 | 0.649 1 | 0.383 8 | 0.095 2 | 0.135 11 | 0.449 9 | 0.432 8 | 0.008 6 | 0.000 1 | 0.518 6 | 0.000 2 | 0.000 2 | 0.000 8 | 0.796 3 | 0.000 2 | 0.000 1 | 0.000 1 | 0.138 10 | 0.000 5 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
Xiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng, Xihui Liu, Kaicheng Yu, Hengshuang Zhao: Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training. CVPR 2024 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
PonderV2 ScanNet200 | 0.346 4 | 0.552 6 | 0.270 6 | 0.175 5 | 0.810 6 | 0.682 6 | 0.950 4 | 0.560 5 | 0.641 8 | 0.761 2 | 0.398 9 | 0.357 8 | 0.570 6 | 0.113 2 | 0.804 4 | 0.603 5 | 0.750 5 | 0.283 3 | 0.681 5 | 0.952 4 | 0.548 4 | 0.874 4 | 0.852 9 | 0.290 8 | 0.700 2 | 0.356 9 | 0.792 4 | 0.445 8 | 0.545 9 | 0.436 8 | 0.351 9 | 0.787 6 | 0.611 6 | 0.050 7 | 0.290 10 | 0.519 9 | 0.000 1 | 0.825 6 | 0.888 4 | 0.842 3 | 0.259 3 | 0.100 2 | 0.558 5 | 0.070 10 | 0.497 6 | 0.247 10 | 0.457 9 | 0.889 2 | 0.248 7 | 0.106 8 | 0.817 9 | 0.691 5 | 0.094 5 | 0.729 3 | 0.636 5 | 0.620 10 | 0.503 9 | 0.660 10 | 0.243 5 | 0.000 3 | 0.212 6 | 0.590 4 | 0.860 6 | 0.400 4 | 0.881 5 | 0.000 3 | 0.202 2 | 0.622 8 | 0.408 7 | 0.499 7 | 0.261 7 | 0.000 1 | 0.385 7 | 0.636 7 | 0.000 4 | 0.000 7 | 0.000 1 | 0.000 4 | 0.433 12 | 0.843 5 | 0.660 5 | 0.574 10 | 0.481 3 | 0.336 4 | 0.677 5 | 0.486 4 | 0.000 3 | 0.030 2 | 0.000 1 | 0.034 5 | 0.000 3 | 0.080 6 | 0.869 8 | 0.000 1 | 0.000 8 | 0.000 9 | 0.540 6 | 0.727 2 | 0.232 13 | 0.115 7 | 0.186 6 | 0.193 7 | 0.000 12 | 0.403 8 | 0.326 5 | 0.103 10 | 0.000 3 | 0.290 3 | 0.392 8 | 0.000 1 | 0.346 6 | 0.062 8 | 0.424 3 | 0.375 5 | 0.431 5 | 0.667 4 | 0.115 10 | 0.082 8 | 0.239 5 | 0.000 1 | 0.504 10 | 0.606 5 | 0.584 8 | 0.000 1 | 0.002 6 | 0.186 6 | 0.104 8 | 0.000 5 | 0.394 4 | 0.384 6 | 0.083 6 | 0.000 5 | 0.007 7 | 0.000 1 | 0.000 2 | 0.880 4 | 0.000 1 | 0.377 8 | 0.000 1 | 0.263 3 | 0.565 2 | 0.000 1 | 0.608 7 | 0.000 1 | 0.000 1 | 0.304 6 | 0.009 7 | 0.924 2 | 0.000 6 | 0.000 7 | 0.000 1 | 0.000 5 | 0.000 1 | 0.128 3 | 0.584 2 | 0.475 5 | 0.412 6 | 0.076 9 | 0.269 3 | 0.621 5 | 0.509 5 | 0.010 4 | 0.000 1 | 0.491 8 | 0.063 1 | 0.000 2 | 0.472 4 | 0.880 2 | 0.000 2 | 0.000 1 | 0.000 1 | 0.179 4 | 0.125 2 | 0.000 3 | 0.441 6 | 0.000 1 | |||||||||||||||||||||||||||||
Haoyi Zhu, Honghui Yang, Xiaoyang Wu, Di Huang, Sha Zhang, Xianglong He, Tong He, Hengshuang Zhao, Chunhua Shen, Yu Qiao, Wanli Ouyang: PonderV2: Pave the Way for 3D Foundataion Model with A Universal Pre-training Paradigm. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
AWCS | 0.305 10 | 0.508 10 | 0.225 10 | 0.142 7 | 0.782 10 | 0.634 13 | 0.937 10 | 0.489 11 | 0.578 10 | 0.721 8 | 0.364 11 | 0.355 9 | 0.515 8 | 0.023 7 | 0.764 10 | 0.523 9 | 0.707 10 | 0.264 7 | 0.633 10 | 0.922 10 | 0.507 11 | 0.886 1 | 0.804 11 | 0.179 11 | 0.436 12 | 0.300 10 | 0.656 12 | 0.529 2 | 0.501 11 | 0.394 9 | 0.296 12 | 0.820 3 | 0.603 7 | 0.131 3 | 0.179 13 | 0.619 2 | 0.000 1 | 0.707 12 | 0.865 10 | 0.773 6 | 0.171 5 | 0.010 6 | 0.484 10 | 0.063 11 | 0.463 10 | 0.254 9 | 0.332 12 | 0.649 9 | 0.220 9 | 0.100 9 | 0.729 11 | 0.613 11 | 0.071 9 | 0.582 11 | 0.628 6 | 0.702 3 | 0.424 11 | 0.749 2 | 0.137 11 | 0.000 3 | 0.142 10 | 0.360 10 | 0.863 4 | 0.305 10 | 0.877 6 | 0.000 3 | 0.173 3 | 0.606 10 | 0.337 10 | 0.478 9 | 0.154 11 | 0.000 1 | 0.253 10 | 0.664 5 | 0.000 4 | 0.000 7 | 0.000 1 | 0.000 4 | 0.626 9 | 0.782 9 | 0.302 12 | 0.602 5 | 0.185 11 | 0.282 6 | 0.651 9 | 0.317 9 | 0.000 3 | 0.000 6 | 0.000 1 | 0.022 9 | 0.000 3 | 0.154 1 | 0.876 7 | 0.000 1 | 0.014 7 | 0.063 8 | 0.029 13 | 0.553 4 | 0.467 2 | 0.084 9 | 0.124 10 | 0.157 12 | 0.049 10 | 0.373 10 | 0.252 8 | 0.097 11 | 0.000 3 | 0.219 4 | 0.542 3 | 0.000 1 | 0.392 4 | 0.172 6 | 0.000 11 | 0.339 7 | 0.417 7 | 0.533 10 | 0.093 11 | 0.115 6 | 0.195 7 | 0.000 1 | 0.516 8 | 0.288 12 | 0.741 3 | 0.000 1 | 0.001 7 | 0.233 5 | 0.056 10 | 0.000 5 | 0.159 5 | 0.334 7 | 0.077 7 | 0.000 5 | 0.000 9 | 0.000 1 | 0.000 2 | 0.749 10 | 0.000 1 | 0.411 6 | 0.000 1 | 0.008 8 | 0.452 9 | 0.000 1 | 0.595 8 | 0.000 1 | 0.000 1 | 0.220 8 | 0.006 8 | 0.894 9 | 0.006 5 | 0.000 7 | 0.000 1 | 0.000 5 | 0.000 1 | 0.112 5 | 0.504 7 | 0.404 8 | 0.551 1 | 0.093 4 | 0.129 13 | 0.484 8 | 0.381 13 | 0.000 9 | 0.000 1 | 0.396 11 | 0.000 2 | 0.000 2 | 0.620 3 | 0.402 13 | 0.000 2 | 0.000 1 | 0.000 1 | 0.142 8 | 0.000 5 | 0.000 3 | 0.512 5 | 0.000 1 | |||||||||||||||||||||||||||||
L3DETR-ScanNet_200 | 0.336 6 | 0.533 9 | 0.279 4 | 0.155 6 | 0.801 8 | 0.689 3 | 0.946 5 | 0.539 7 | 0.660 6 | 0.759 3 | 0.380 10 | 0.333 10 | 0.583 2 | 0.000 10 | 0.788 7 | 0.529 8 | 0.740 6 | 0.261 8 | 0.679 7 | 0.940 9 | 0.525 9 | 0.860 7 | 0.883 5 | 0.226 9 | 0.613 7 | 0.397 4 | 0.720 9 | 0.512 4 | 0.565 8 | 0.620 2 | 0.417 4 | 0.775 9 | 0.629 4 | 0.158 2 | 0.298 8 | 0.579 8 | 0.000 1 | 0.835 2 | 0.883 5 | 0.927 1 | 0.114 8 | 0.079 4 | 0.511 8 | 0.073 9 | 0.508 4 | 0.312 4 | 0.629 4 | 0.861 4 | 0.192 12 | 0.098 11 | 0.908 2 | 0.636 9 | 0.032 13 | 0.563 13 | 0.514 11 | 0.664 4 | 0.505 8 | 0.697 6 | 0.225 7 | 0.000 3 | 0.264 2 | 0.411 9 | 0.860 6 | 0.321 9 | 0.960 1 | 0.058 2 | 0.109 10 | 0.776 2 | 0.526 3 | 0.557 2 | 0.303 6 | 0.000 1 | 0.339 8 | 0.712 4 | 0.000 4 | 0.014 5 | 0.000 1 | 0.000 4 | 0.638 8 | 0.856 3 | 0.641 6 | 0.579 9 | 0.107 13 | 0.119 11 | 0.661 7 | 0.416 5 | 0.000 3 | 0.000 6 | 0.000 1 | 0.007 13 | 0.000 3 | 0.067 8 | 0.910 4 | 0.000 1 | 0.000 8 | 0.000 9 | 0.463 7 | 0.448 5 | 0.294 12 | 0.324 1 | 0.293 2 | 0.211 6 | 0.108 6 | 0.448 7 | 0.068 13 | 0.141 5 | 0.000 3 | 0.330 2 | 0.699 1 | 0.000 1 | 0.256 7 | 0.192 4 | 0.000 11 | 0.355 6 | 0.418 6 | 0.209 13 | 0.146 8 | 0.679 1 | 0.101 13 | 0.000 1 | 0.503 11 | 0.687 1 | 0.671 5 | 0.000 1 | 0.000 8 | 0.174 7 | 0.117 4 | 0.000 5 | 0.122 6 | 0.515 2 | 0.104 4 | 0.259 2 | 0.312 3 | 0.000 1 | 0.000 2 | 0.765 9 | 0.000 1 | 0.369 10 | 0.000 1 | 0.183 5 | 0.422 10 | 0.000 1 | 0.646 3 | 0.000 1 | 0.000 1 | 0.565 2 | 0.001 10 | 0.125 13 | 0.010 4 | 0.002 6 | 0.000 1 | 0.487 1 | 0.000 1 | 0.075 12 | 0.548 3 | 0.420 7 | 0.233 12 | 0.082 7 | 0.138 10 | 0.430 10 | 0.427 9 | 0.000 9 | 0.000 1 | 0.549 5 | 0.000 2 | 0.000 2 | 0.074 7 | 0.409 12 | 0.000 2 | 0.000 1 | 0.000 1 | 0.152 6 | 0.051 3 | 0.000 3 | 0.598 4 | 0.000 1 | |||||||||||||||||||||||||||||
Yanmin Wu, Qiankun Gao, Renrui Zhang, Jian Zhang: Language-Assisted 3D Scene Understanding. arXiv23.12 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
LGround | 0.272 11 | 0.485 11 | 0.184 11 | 0.106 11 | 0.778 11 | 0.676 8 | 0.932 11 | 0.479 13 | 0.572 11 | 0.718 10 | 0.399 8 | 0.265 11 | 0.453 12 | 0.085 3 | 0.745 11 | 0.446 11 | 0.726 9 | 0.232 11 | 0.622 11 | 0.901 11 | 0.512 10 | 0.826 11 | 0.786 12 | 0.178 12 | 0.549 8 | 0.277 11 | 0.659 11 | 0.381 11 | 0.518 10 | 0.295 13 | 0.323 10 | 0.777 8 | 0.599 8 | 0.028 9 | 0.321 7 | 0.363 12 | 0.000 1 | 0.708 11 | 0.858 11 | 0.746 9 | 0.063 11 | 0.022 5 | 0.457 11 | 0.077 8 | 0.476 8 | 0.243 11 | 0.402 10 | 0.397 13 | 0.233 8 | 0.077 13 | 0.720 13 | 0.610 12 | 0.103 4 | 0.629 9 | 0.437 13 | 0.626 9 | 0.446 10 | 0.702 5 | 0.190 9 | 0.005 1 | 0.058 12 | 0.322 11 | 0.702 12 | 0.244 11 | 0.768 10 | 0.000 3 | 0.134 9 | 0.552 11 | 0.279 12 | 0.395 11 | 0.147 12 | 0.000 1 | 0.207 11 | 0.612 10 | 0.000 4 | 0.000 7 | 0.000 1 | 0.000 4 | 0.658 7 | 0.566 11 | 0.323 11 | 0.525 13 | 0.229 10 | 0.179 8 | 0.467 13 | 0.154 12 | 0.000 3 | 0.002 4 | 0.000 1 | 0.051 1 | 0.000 3 | 0.127 2 | 0.703 10 | 0.000 1 | 0.000 8 | 0.216 1 | 0.112 12 | 0.358 8 | 0.547 1 | 0.187 5 | 0.092 12 | 0.156 13 | 0.055 8 | 0.296 11 | 0.252 8 | 0.143 4 | 0.000 3 | 0.014 10 | 0.398 7 | 0.000 1 | 0.028 12 | 0.173 5 | 0.000 11 | 0.265 12 | 0.348 11 | 0.415 12 | 0.179 4 | 0.019 12 | 0.218 6 | 0.000 1 | 0.597 6 | 0.274 13 | 0.565 9 | 0.000 1 | 0.012 5 | 0.000 8 | 0.039 12 | 0.022 2 | 0.000 8 | 0.117 11 | 0.000 8 | 0.000 5 | 0.000 9 | 0.000 1 | 0.000 2 | 0.324 12 | 0.000 1 | 0.384 7 | 0.000 1 | 0.000 9 | 0.251 13 | 0.000 1 | 0.566 9 | 0.000 1 | 0.000 1 | 0.066 10 | 0.404 1 | 0.886 10 | 0.199 1 | 0.000 7 | 0.000 1 | 0.059 3 | 0.000 1 | 0.136 1 | 0.540 4 | 0.127 13 | 0.295 9 | 0.085 6 | 0.143 6 | 0.514 6 | 0.413 11 | 0.000 9 | 0.000 1 | 0.498 7 | 0.000 2 | 0.000 2 | 0.000 8 | 0.623 9 | 0.000 2 | 0.000 1 | 0.000 1 | 0.132 12 | 0.000 5 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
David Rozenberszki, Or Litany, Angela Dai: Language-Grounded Indoor 3D Semantic Segmentation in the Wild. arXiv | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Minkowski 34D | 0.253 12 | 0.463 12 | 0.154 13 | 0.102 12 | 0.771 12 | 0.650 12 | 0.932 11 | 0.483 12 | 0.571 12 | 0.710 11 | 0.331 12 | 0.250 12 | 0.492 10 | 0.044 4 | 0.703 12 | 0.419 13 | 0.606 13 | 0.227 12 | 0.621 12 | 0.865 13 | 0.531 7 | 0.771 13 | 0.813 10 | 0.291 7 | 0.484 11 | 0.242 12 | 0.612 13 | 0.282 13 | 0.440 13 | 0.351 11 | 0.299 11 | 0.622 12 | 0.593 9 | 0.027 10 | 0.293 9 | 0.310 13 | 0.000 1 | 0.757 10 | 0.858 11 | 0.737 11 | 0.150 6 | 0.164 1 | 0.368 13 | 0.084 6 | 0.381 13 | 0.142 13 | 0.357 11 | 0.720 8 | 0.214 10 | 0.092 12 | 0.724 12 | 0.596 13 | 0.056 10 | 0.655 6 | 0.525 10 | 0.581 13 | 0.352 13 | 0.594 12 | 0.056 13 | 0.000 3 | 0.014 13 | 0.224 12 | 0.772 11 | 0.205 13 | 0.720 12 | 0.000 3 | 0.159 5 | 0.531 12 | 0.163 13 | 0.294 12 | 0.136 13 | 0.000 1 | 0.169 12 | 0.589 11 | 0.000 4 | 0.000 7 | 0.000 1 | 0.002 2 | 0.663 6 | 0.466 13 | 0.265 13 | 0.582 8 | 0.337 9 | 0.016 12 | 0.559 11 | 0.084 13 | 0.000 3 | 0.000 6 | 0.000 1 | 0.036 4 | 0.000 3 | 0.125 3 | 0.670 11 | 0.000 1 | 0.102 1 | 0.071 7 | 0.164 11 | 0.406 6 | 0.386 5 | 0.046 12 | 0.068 13 | 0.159 11 | 0.117 4 | 0.284 12 | 0.111 12 | 0.094 12 | 0.000 3 | 0.000 13 | 0.197 13 | 0.000 1 | 0.044 11 | 0.013 11 | 0.002 10 | 0.228 13 | 0.307 13 | 0.588 8 | 0.025 13 | 0.545 3 | 0.134 11 | 0.000 1 | 0.655 4 | 0.302 11 | 0.282 13 | 0.000 1 | 0.060 2 | 0.000 8 | 0.035 13 | 0.000 5 | 0.000 8 | 0.097 13 | 0.000 8 | 0.000 5 | 0.005 8 | 0.000 1 | 0.000 2 | 0.096 13 | 0.000 1 | 0.334 12 | 0.000 1 | 0.000 9 | 0.274 12 | 0.000 1 | 0.513 12 | 0.000 1 | 0.000 1 | 0.280 7 | 0.194 5 | 0.897 8 | 0.000 6 | 0.000 7 | 0.000 1 | 0.000 5 | 0.000 1 | 0.108 8 | 0.279 13 | 0.189 12 | 0.141 13 | 0.059 12 | 0.272 2 | 0.307 13 | 0.445 6 | 0.003 7 | 0.000 1 | 0.353 12 | 0.000 2 | 0.026 1 | 0.000 8 | 0.581 11 | 0.001 1 | 0.000 1 | 0.000 1 | 0.093 13 | 0.002 4 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
C. Choy, J. Gwak, S. Savarese: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. CVPR 2019 | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
CSC-Pretrain | 0.249 13 | 0.455 13 | 0.171 12 | 0.079 13 | 0.766 13 | 0.659 11 | 0.930 13 | 0.494 10 | 0.542 13 | 0.700 13 | 0.314 13 | 0.215 13 | 0.430 13 | 0.121 1 | 0.697 13 | 0.441 12 | 0.683 12 | 0.235 10 | 0.609 13 | 0.895 12 | 0.476 13 | 0.816 12 | 0.770 13 | 0.186 10 | 0.634 4 | 0.216 13 | 0.734 7 | 0.340 12 | 0.471 12 | 0.307 12 | 0.293 13 | 0.591 13 | 0.542 11 | 0.076 6 | 0.205 12 | 0.464 11 | 0.000 1 | 0.484 13 | 0.832 13 | 0.766 7 | 0.052 12 | 0.000 7 | 0.413 12 | 0.059 12 | 0.418 12 | 0.222 12 | 0.318 13 | 0.609 11 | 0.206 11 | 0.112 7 | 0.743 10 | 0.625 10 | 0.076 7 | 0.579 12 | 0.548 9 | 0.590 12 | 0.371 12 | 0.552 13 | 0.081 12 | 0.003 2 | 0.142 10 | 0.201 13 | 0.638 13 | 0.233 12 | 0.686 13 | 0.000 3 | 0.142 7 | 0.444 13 | 0.375 9 | 0.247 13 | 0.198 10 | 0.000 1 | 0.128 13 | 0.454 13 | 0.019 2 | 0.097 1 | 0.000 1 | 0.000 4 | 0.553 10 | 0.557 12 | 0.373 9 | 0.545 12 | 0.164 12 | 0.014 13 | 0.547 12 | 0.174 11 | 0.000 3 | 0.002 4 | 0.000 1 | 0.037 3 | 0.000 3 | 0.063 9 | 0.664 12 | 0.000 1 | 0.000 8 | 0.130 2 | 0.170 10 | 0.152 13 | 0.335 8 | 0.079 10 | 0.110 11 | 0.175 10 | 0.098 7 | 0.175 13 | 0.166 11 | 0.045 13 | 0.207 1 | 0.014 10 | 0.465 5 | 0.000 1 | 0.001 13 | 0.001 13 | 0.046 8 | 0.299 11 | 0.327 12 | 0.537 9 | 0.033 12 | 0.012 13 | 0.186 8 | 0.000 1 | 0.205 12 | 0.377 10 | 0.463 12 | 0.000 1 | 0.058 3 | 0.000 8 | 0.055 11 | 0.041 1 | 0.000 8 | 0.105 12 | 0.000 8 | 0.000 5 | 0.000 9 | 0.000 1 | 0.000 2 | 0.398 11 | 0.000 1 | 0.308 13 | 0.000 1 | 0.000 9 | 0.319 11 | 0.000 1 | 0.543 10 | 0.000 1 | 0.000 1 | 0.062 11 | 0.004 9 | 0.862 12 | 0.000 6 | 0.000 7 | 0.000 1 | 0.000 5 | 0.000 1 | 0.123 4 | 0.316 12 | 0.225 11 | 0.250 11 | 0.094 3 | 0.180 5 | 0.332 12 | 0.441 7 | 0.000 9 | 0.000 1 | 0.310 13 | 0.000 2 | 0.000 2 | 0.000 8 | 0.592 10 | 0.000 2 | 0.000 1 | 0.000 1 | 0.203 2 | 0.000 5 | 0.000 3 | 0.000 7 | 0.000 1 | |||||||||||||||||||||||||||||
Ji Hou, Benjamin Graham, Matthias Nießner, Saining Xie: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. CVPR 2021 |